Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation
Anthropic says it has cut the extraction of Claude's internal reasoning tokens by 90 to 99 percent. The company links the large-scale distillation attacks to Chinese companies Zhipu and Moonshot, and has already banned tens of thousands of accounts.
Via The Decoder
Anthropic is battling large-scale distillation attacks on its Claude models. In these attacks, companies systematically copy an AI model's capabilities to train their own, smaller models. Anthropic says its new defenses have cut the volume of extracted reasoning tokens, the model's internal chain-of-thought steps, by 90 to 99 percent. Attackers use networks of hundreds of thousands of fake accounts to pull it off.
According to Anthropic, successful distillation attempts dropped sharply after its defenses went live. | Image: Anthropic
Anthropic…
Courtesy
This story was originally published by The Decoder. All rights belong to the original publisher.
Read the original on the-decoder.com ↗